Author:
Kuhse Daniel,Teper Harun,Hakert Christian,Chen Jian-Jia
Abstract
Abstract
We propose two complementary research directions, “Time for ML” and “ML for Time”, that we believe to be critical for the deployment of machine-learning (ML) applications in time-sensitive applications. “Time for ML” refers to ML systems that are aware of and can adapt to dynamic time constraints regarding their execution, while “ML for Time” refers to ML systems that are aware of and can deal with data’s temporal aspects, such as misalignment. We believe these two directions are complementary and can be combined to provide more robust and reliable machine learning systems.
Funder
Bundesministerium für Bildung und Forschung
Technische Universität Dortmund
Publisher
Springer Science and Business Media LLC
Reference32 articles.
1. Breiman L, Friedman J, Olshen RA, Stone CJ (1984) Classification and regression trees. CRC Press, Boca Raton
2. Cai H, Gan C, Wang T, Zhang Z, Han S (2019) Once-for-all: Train one network and specialize it for efficient deployment. Preprint at arXiv:1908.09791
3. Coulom R (2006) Efficient selectivity and backup operators in Monte–Carlo tree search. In: International Conference on Computers and Games, pp. 72–83 . Springer
4. Davare A, Zhu Q, Di Natale M, Pinello C, Kanajan S, Sangiovanni-Vincentelli A (2007) Period optimization for hard real-time distributed automotive systems. In: Proceedings of the 44th Annual Design Automation Conference. DAC ’07, pp. 278–283. Association for Computing Machinery, New York, NY, USA
5. Elhoushi M, Shrivastava A, Liskovich D, Hosmer B, Wasti B, Lai L, Mahmoud A, Acun B, Agarwal S, Roman A, et al.: Layer skip: enabling early exit inference and self-speculative decoding. Preprint at arXiv:2404.16710 (2024)